Motion Objects Detection Based on Higher Order Statistics and HSV Color Space

For the inherent problem of the moving object segmentation based on the background subtraction criteria, the present paper proposes a novel shadow elimination algorithm based on HSV color space and the higher order statistics. The proposed algorithm can distinguish the changes occurring from background disturbing effects such as noise, shadows and illumination changes. It includes two stages: pre-detection of moving object and shadow elimination. Simulation experiment results show that the proposed algorithm cannot only eliminate the shadows of moving objects effectively, but can improve the accuracy of object detection. Moreover, our proposed algorithm is feasible for practical application due to setting parameters automatically.